{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/generalized-random-forests","title":"Generalized Random Forests","arxiv_id":"1610.01271","date":"2016-10-05","proceeding":null,"authors":["Susan Athey","Julie Tibshirani","Stefan Wager"],"abstract":"We propose generalized random forests, a method for non-parametric\nstatistical estimation based on random forests (Breiman, 2001) that can be used\nto fit any quantity of interest identified as the solution to a set of local\nmoment equations. Following the literature on local maximum likelihood\nestimation, our method considers a weighted set of nearby training examples;\nhowever, instead of using classical kernel weighting functions that are prone\nto a strong curse of dimensionality, we use an adaptive weighting function\nderived from a forest designed to express heterogeneity in the specified\nquantity of interest. We propose a flexible, computationally efficient\nalgorithm for growing generalized random forests, develop a large sample theory\nfor our method showing that our estimates are consistent and asymptotically\nGaussian, and provide an estimator for their asymptotic variance that enables\nvalid confidence intervals. We use our approach to develop new methods for\nthree statistical tasks: non-parametric quantile regression, conditional\naverage partial effect estimation, and heterogeneous treatment effect\nestimation via instrumental variables. A software implementation, grf for R and\nC++, is available from CRAN.","url_abs":"http://arxiv.org/abs/1610.01271v4","url_pdf":"http://arxiv.org/pdf/1610.01271v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"generalized-random-forests","repo_url":"https://github.com/swager/grf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"generalized-random-forests","repo_url":"https://github.com/ischeinfeld/natality","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"generalized-random-forests","repo_url":"https://github.com/rajkumarkarthik/mgrf-develop","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"generalized-random-forests","repo_url":"https://github.com/till-tietz/rcf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generalized-random-forests","repo_url":"https://github.com/vshirvaikar/rrcf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"heterogeneous-treatment-effect-estimation","task_name":"Heterogeneous Treatment Effect Estimation"},{"task_slug":"quantile-regression","task_name":"quantile regression"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.01271","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}